Papers › Can Large Language Models be Good Path Planners? A Benchmark and Investigation on...

Can Large Language Models be Good Path Planners? A Benchmark and Investigation on Spatial-temporal Reasoning

5 Oct 2023arXiv:2310.03249archive 2025-07-28

Mohamed Aghzal, Erion Plaku, Ziyu Yao

Large language models (LLMs) have achieved remarkable success across a wide spectrum of tasks; however, they still face limitations in scenarios that demand long-term planning and spatial reasoning. To facilitate this line of research, in this work, we propose a new benchmark, termed Path Planning from Natural Language (PPNL). Our benchmark evaluates LLMs' spatial-temporal reasoning by formulating ''path planning'' tasks that require an LLM to navigate to target locations while avoiding obstacles and adhering to constraints. Leveraging this benchmark, we systematically investigate LLMs including GPT-4 via different few-shot prompting methodologies as well as BART and T5 of various sizes via fine-tuning. Our experimental results show the promise of few-shot GPT-4 in spatial reasoning, when it is prompted to reason and act interleavedly, although it still fails to perform long-term temporal reasoning. In contrast, while fine-tuned LLMs achieved impressive results on in-distribution reasoning tasks, they struggled to generalize to larger environments or environments with more obstacles.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 28 code samples harvested from 1 repository linked to this paper: 28 ran (of which 0 constructed an object rather than computing a result; 28 with no instrument failure: 0 honoured, 0 violated, 28 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 28 samples from 1 repository, 28 ran (28 with no instrument failure; 0 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written on 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

mohamedaghzal/llms-as-path-planners officialmentioned in papermentioned on GitHubpytorchSyntology: 28 samples, 28 ran (0 instrument-failed) · 0 unverified report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

28 samples harvested: 28 ran (of which 0 constructed an object rather than computing a result; 28 with no instrument failure: 0 honoured, 0 violated, 28 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

28ran

Licence: 28 of the 28 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from mohamedaghzal/llms-as-path-planners. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

mohamedaghzal/llms-as-path-planners official repository 28 samples, 28 ran (0 instrument-failed) · 0 unverified
a_star gpt-4-path-planning/src/generate_samples.py ran no licence file found · pointer only · 1d7ecad86c4cf33d · report fixture: signature grid:ndarray/2/int, start:tuple/1/int, goal:tuple/1/int · returned list · level recorded 2026-09-24
actions_and_effects ppnl-spatial-temporal-reasoning/ICL/actions_and_effect_prompts.py ran fingerprinted no licence file found · pointer only · f514998c2d24dde3 · report fixture: signature actions:str/0/str, path:list/1/tuple · returned str · level recorded 2026-09-24
build_path gpt-4-path-planning/src/place_agent_goals_sg.py ran no licence file found · pointer only · e668aeb35a33a774 · report fixture: signature grid:list/1/list, start:tuple/1/int, desired_distance:int/0/int, obstacles:list/1/list · returned list · level recorded 2026-09-24
construct_grid gpt-4-path-planning/src/place_agent_goals_sg.py ran no licence file found · pointer only · 8419ce244e148b28 · report fixture: signature n:int/0/int, obstacles:list/1/list · returned list · level recorded 2026-09-24
count_obstacles ppnl-spatial-temporal-reasoning/ICL/actions_and_effect_prompts.py ran no licence file found · pointer only · f7e0e94c07eec3e4 · report fixture: signature world:list/1/list · returned int · level recorded 2026-09-24
draw_path gpt-4-path-planning/src/prompting.py ran no licence file found · pointer only · 5a4054d663046894 · report fixture: signature org_grid:list/1/list, path:str/0/str, init:tuple/1/int · returned list · level recorded 2026-09-24
exact_match in 23 papers gpt-4-path-planning/src/evaluate.py ran fingerprinted no licence file found · pointer only · 806fb301720451ec · report fixture: signature correct:str/0/str, predicted:str/0/str · returned bool · level recorded 2026-09-24
fixed_length gpt-4-path-planning/src/helpers.py ran no licence file found · pointer only · caa8df4c4d1fd565 · report fixture: signature iid_samples:list/1/dict, ood_samples:list/1/dict, values:list/1/int, n_instances:int/0/int · returned dict · level recorded 2026-09-24
generate_code in 6 papers gpt-4-path-planning/src/generate_samples.py ran no licence file found · pointer only · c274f392ee719051 · report fixture: signature x:int/0/int, y:int/0/int, obstacles:list/1/list, goals:list/1/list, initial_loc:list/1/int · returned str · level recorded 2026-09-24
generate_code_alternate_column gpt-4-path-planning/src/representations.py ran no licence file found · pointer only · 0702ff5547719980 · report fixture: signature x:int/0/int, y:int/0/int, obstacles:list/1/tuple, goals:list/1/tuple, initial_loc:list/1/int · returned str · level recorded 2026-09-24
generate_code_rectangle gpt-4-path-planning/src/representations.py ran no licence file found · pointer only · b1c836fbb3f4d4fc · report fixture: signature x:int/0/int, y:int/0/int, obstacles:list/1/empty, goals:list/1/tuple, initial_loc:tuple/1/int, points:list/1/list · returned str · level recorded 2026-09-24
generate_code_spiral gpt-4-path-planning/src/representations.py ran no licence file found · pointer only · 35a7867d3c2e93af · report fixture: signature size_x:int/0/int, size_y:int/0/int, obstacles:list/1/tuple, goals:list/1/tuple, initial_loc:tuple/1/int · returned str · level recorded 2026-09-24
generate_effects gpt-4-path-planning/src/prompting.py ran no licence file found · pointer only · 00e00e527a7e268c · report fixture: signature sample:dict/0/?, start:tuple/1/int, goal:tuple/1/int · returned str · level recorded 2026-09-24
generate_grid in 14 papers gpt-4-path-planning/src/generate_samples.py ran no licence file found · pointer only · 89b81366df015ab8 · report fixture: signature grid:list/1/list · returned str · level recorded 2026-09-24
generate_worlds gpt-4-path-planning/src/place_agent_goals_sg.py ran no licence file found · pointer only · cebb72c7aecd9c49 · report fixture: signature obstacles:list/1/list, n:int/0/int, n_goals:int/0/int, trials:int/0/int, low_bound:int/0/int, high_bound:int/0/int, vals:NoneType/0/? · returned list · level recorded 2026-09-24
get_actual ppnl-spatial-temporal-reasoning/ICL/parse_react_mg_path.py ran no licence file found · pointer only · d3e9e3908a9df9c8 · report fixture: signature path:list/1/list, world:list/1/list · returned str · level recorded 2026-09-24
is_row gpt-4-path-planning/src/planning_samples.py ran no licence file found · pointer only · 3a2159f19cba31c7 · report fixture: signature world:list/1/list · returned bool · level recorded 2026-09-24
one_opening_per_column gpt-4-path-planning/src/one_entrance.py ran no licence file found · pointer only · 1ddb64e34d0ffc15 · report fixture: signature size:int/0/int, even_or_odd:bool/0/bool · returned tuple · level recorded 2026-09-24
one_opening_per_row gpt-4-path-planning/src/one_entrance.py ran no licence file found · pointer only · f62c1ffb342ad79d · report fixture: signature size:int/0/int, even_or_odd:bool/0/bool · returned tuple · level recorded 2026-09-24
out_of_bounds gpt-4-path-planning/src/prompting.py ran no licence file found · pointer only · a93c8460f75834dc · report fixture: signature grid:list/1/list, position:tuple/1/int · returned bool · level recorded 2026-09-24
parse_react_path ppnl-spatial-temporal-reasoning/ICL/parse_react_mg_path.py ran no licence file found · pointer only · 2aa266d417a4012c · report fixture: signature history:list/1/list, prompt:str/0/str · returned list · level recorded 2026-09-24
rectangle in 7 papers gpt-4-path-planning/src/geometries.py ran no licence file found · pointer only · ba3aa7daeaf50708 · report fixture: signature size:int/0/int, n_blocks:int/0/int · returned tuple · level recorded 2026-09-24
sample in 167 papers
census: 8 implementations from 9 papers, 7 distinct outputs across 5 buckets, one shared input per bucket
gpt-4-path-planning/src/one_entrance.py ran no licence file found · pointer only · 822d5128406dc0b4 · report fixture: signature shape:int/0/int, choice:str/0/str, target:int/0/int · returned list · level recorded 2026-09-24
single_environment gpt-4-path-planning/src/helpers.py ran no licence file found · pointer only · 8ed9120665b11d99 · report fixture: signature iid_samples:list/1/dict, ood_samples:list/1/dict, n_instances:int/0/int, geometry:str/0/str · returned dict · level recorded 2026-09-24
spiral_maze gpt-4-path-planning/src/geometries.py ran no licence file found · pointer only · 8d0323e6656ee492 · report fixture: signature size:int/0/int · returned tuple · level recorded 2026-09-24
success_sg gpt-4-path-planning/src/evaluate.py ran no licence file found · pointer only · d74bce6422f92cd8 · report fixture: signature grid:list/1/list, predicted:str/0/str, start:tuple/1/int · returned bool · level recorded 2026-09-24
triangle in 8 papers gpt-4-path-planning/src/geometries.py ran no licence file found · pointer only · 02579eedf3922c00 · report fixture: signature size:int/0/int, orientation:str/0/str, triangle_size:int/0/int · returned tuple · level recorded 2026-09-24
valid_position gpt-4-path-planning/src/evaluate.py ran no licence file found · pointer only · 4ac5d326cb14bb91 · report fixture: signature pos:list/1/int, grid:list/1/list · returned bool · level recorded 2026-09-24

Tasks

NavigateSpatial Reasoning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Absolute Position EncodingsAdafactorAdamAttentionAttention DropoutBARTBPEDense ConnectionsDropoutGPT-4Gated Linear UnitInverse Square Root ScheduleLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSentencePieceSoftmaxT5Transformer

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections